Product roadmap

Choose what information an Assistant uses to answer, whether that's the web, your whole Knowledge Center, or just the assets you pick.

Specify where each project gets its information, such as from the web, the Knowledge Center, or specific assets.

Upload one or more files from your device and use them in your conversation with the Assistant.

Choose how much thinking a command gets so quick tasks come back fast and bigger ones get deeper reasoning.

Set a command to repeat automatically on a schedule, like generating a weekly report or sending monthly reminders to anyone with overdue training.

Generate natural-sounding audio, like a voiceover, just by describing what you need or sharing a script.

Create short videos from a simple description, such as a welcome message for new hires or a quick explainer.

Work on longer content, such as a document draft, in a canvas beside the chat. Ask the Assistant to make changes as you go.

Save a canvas from your chat with the Assistant as a FlexDoc in the Knowledge Center, where you can share, edit, and assign it like any other asset.

Share a link that opens a video at a specific moment or a PDF at a specific page.

Turn off downloading for an asset when people should only view it in Joy.

Upload your own video files and embed them in a FlexDoc, alongside YouTube, Vimeo, and Twitch videos.

Translate your content into other languages so people can read it in the language they prefer.

Turn a document you already have (a policy PDF, a slide deck, a product guide, or a recorded call) into a course outline with bite-sized lessons, a knowledge check, and activities. Content comes only from approved sources, and you can edit every draft before it goes out.

Present lesson material with live content blocks (rich text, charts, key performance indicator (KPI) metrics, dashboards, Mermaid and interactive flow diagrams, tabs, tables, comparison tables, images, video, code, flashcards, forms, callouts, and sandboxed HTML). Each block is generated from your own documents.

Choose from 17 self-scoring question types, including a multi-question quiz engine, single- and multi-select, true or false, fill-in-the-blank, short answer, matching, categorization and sorting, hot spots, labeling, and ordering. Each one is generated from your source material and gives instant, color-coded feedback.

Generate six kinds of practice from your sources: Knowledge Coach (Socratic walkthrough), Conversational Scenario (in-character dialogue), Situational Scenario (step-by-step problem solving), Data Entry Scenario (field-by-field form practice), Software Simulation (watch, try, and prove it, from screenshots), and a Custom guided experience. Each can be graded or ungraded and adapts to what the learner does.

Get a custom coded interactivity (a browser-based widget or simulation) scoped and built for a specific course when no template fits.

Play any course in Presentation mode, which draws content onto the screen in sync with AI-generated narration in the voice and language you choose. The narration describes images, summarizes tables, and reveals bullets as it speaks. Progress is saved for each element, so a half-finished course resumes where the learner left off.

Get help from a page-aware Learning Assistant docked alongside every course's content. It can summarize the current page, quiz the learner on it, pull out key takeaways, or explain concepts. It's included in the SCORM export, so it works in any learning management system (LMS).

Offer learners who fail a quiz a one-on-one coaching session on the pages they missed before they retry. Quizzes come in three depths: recognition, open-ended AI-graded recall, and a recall challenge.

Generate the same course, including quizzes, roleplays, and coaching, in dozens of languages from one source document, with no separate translation step. The source can be in one language while quizzes and answers are in others.

Apply themes and your organization's branding to a course once, and they carry across the whole course.

Export a finished course as a SCORM package (SCORM 1.2 or 2004) in one click, then import it into any standards-compliant learning management system (LMS) with no re-authoring. Completion and scores report back through the LMS.

Count a course as complete only when the learner reaches a passing score, so completion means mastery. Design certificate templates once and assign them to assets, and Joy issues a branded certificate with the learner's details on completion, ready to download from Tasks.

Give completions a valid-until date, and the task comes back automatically for recertification when it lapses.

Give learners an AI-written debrief when they finish an assignment, summarizing how they did and what to revisit. Joy's Learning Assistants also leave progress notes and an end-of-task summary on each assignment.

See completion rates, average quiz scores, and at-risk learners at a glance, by person and group, and export reports for audits or stakeholders. Joy keeps the same completion record whether a course runs in Joy or as an exported SCORM package in your learning management system (LMS).

Pick users and assets by browsing your organization and Knowledge Center in a window, anywhere you choose them, such as when you assign training.

Get notifications in Joy about activity that matters to you.

Connect Joy to Slack and Microsoft Teams so your team can work with Joy where conversations already happen.

Control what individuals and groups can see and do with a more flexible permissions system that goes beyond the current two roles.

Sign in to Joy with your company's identity provider through enterprise single sign-on (SSO). Identity is verified on the server, and users are provisioned on demand when Joy is embedded in an LMS.

Organize users into groups and segments that reflect how your organization is set up.

Build a multi-question quiz from your source material, with a progress bar, an optional timer, scoring for each question, and a results screen. The score counts toward completion.

Present options where only one answer is correct, with color-coded feedback as soon as the learner chooses.

Present options where several answers may be correct, scored all-or-none or with partial credit.

Show a statement from your material for the learner to judge true or false.

Ask the learner to type the missing word or phrase into a blank, and check the answer right away.

Accept a free-text response and grade it with your choice of scoring styles.

Have the learner pair items from two sets drawn from your source material.

Ask the learner to sort items into the correct categories, by dropdown or drag-and-drop.

Challenge the learner to pick out the correct region of an image or passage of text.

Ask the learner to label parts of an image or diagram.

Have the learner put items in the correct order, by dropdown or drag-and-drop. The result counts toward completion and scoring.

Walk the learner through your material section by section with Socratic questioning until they can explain it back.

Put the learner in an in-character dialogue based on your content, with coaching feedback after each reply.

Step the learner through a problem that isn't a conversation, decision by decision. It can be graded or ungraded.

Have the learner complete a form field by field, with live validation.

Build a watch, try, and prove-it walkthrough of a workflow from screenshots you upload.

Set up an Assistant-style conversation with your own AI instructions, and it adapts to what the learner says.

Show bar, line, pie, donut, scatter, and radar charts inside a lesson, generated from your documents and data.

Present key performance indicator (KPI) metrics and mini dashboards in a lesson, drawn from your source material.

Explain processes and relationships with Mermaid and interactive flow diagrams inside a lesson.

Lay out side-by-side comparison tables generated from your content.

Add custom HTML and CSS widgets to a lesson, safely sandboxed.

Flag an Assistant's answer as incorrect or missing information so it can be reviewed and improved.

Use the Assistant inside other apps, such as SmarterU LMS, so you can ask questions without leaving the tool you're in.

Use Joy on your phone or tablet with mobile apps for iOS and Android.

Paste longer or more varied content into the chat and have it handled cleanly so your message stays easy to read and the Assistant gets everything you shared.

Pin a command so it stays active as you keep chatting, until you unpin it. You'll always see what's pinned at the top of the chat, and you can still use other commands alongside it.

Get clearer, more polished charts, diagrams, and other visual responses from the Assistant.

Bring files from OneDrive into the Knowledge Center as links, so you can preview them in Joy and the Assistant can reference them.

Upload notes and documentation saved as Markdown (MD) files, and the Assistant can reference them.

Manage each folder from its own admin panel, and delete folders you no longer need.

Open an uploaded SCORM course in Joy to preview it, and assign it as a task like any other asset.

Export a Knowledge Center asset to your learning management system (LMS) and launch it from there.

Let a connector take actions in a source system instead of only reading from it, turned on only where IT approves.

Get a SOC 2 Type II attestation covering security, availability, and confidentiality controls. It adds an independent audit to source-grounded answers and to the encryption and audit logging controls.

Get an independent ISO 27001 audit of the information-security management system.

Count on GDPR readiness for handling and protecting the personal data of people in the EU.

Safeguard protected health information (PHI) with HIPAA readiness. HIPAA is a US law.

Manage your account in one place, including your billing information.

Set a time frame when you assign an asset, and anyone who already completed it within that time is credited instead of being assigned it again.

Connect your business tools (such as CRM, support, and project systems), HR systems, corporate and academic learning platforms, and collaboration tools so their content is searchable alongside the Knowledge Center. Ask questions that span several systems and get one grounded, cited answer.

Choose from a catalog of 73 pre-built connectors across communication, CRM, data, e-sign, finance, HR, knowledge, LMS, marketing, project management, support, survey, and video tools, including Salesforce, Slack, SharePoint, Google Drive, Workday, Jira, Zendesk, and HubSpot. Add each one without custom development.

Keep connectors read-only and permission-aware by default. Each person sees only the data they can already access in the source system, and nothing in the source system changes.

Connect a system in a guided flow: sign in, choose what to make searchable, and bring that content into search alongside the Knowledge Center.

Connect your own services and systems beyond the pre-built library through REST APIs, GraphQL, webhooks, and other interfaces. Cross-system search then reaches in-house and niche tools under the same read-only, permission-aware model.

Trace every answer to its source. Answers are restricted to admin-approved sources rather than the open web, every answer is cited, and audit logging covers administrative actions.

Link a file from your Google Drive to the Knowledge Center, preview it in Joy, and use it as a source for the Assistant. When the file changes in Drive, Joy picks up the update.

Keep data encrypted in transit and at rest with 256-bit encryption. Your content is never used to train AI models, and you control how long it's kept.

Paste a file into the chat and ask about it. Get a quick summary of a report or have a policy draft checked for gaps.

Create a draft from a published FlexDoc, edit it with auto-save, and switch between the draft and published views. Click Publish to make your changes public, and restore an earlier version from Version history. Each doc has one draft at a time.

Manage each asset from its admin panel (Overview and Details): title, active or inactive status (inactive assets are visible to admins only), an editable About description, created and edited details, and an API ID for referencing the asset in integrations.

Upload PowerPoint presentations (PPT and PPTX) to the Knowledge Center and ask the Assistant about them, like any other document.

Upload SCORM course packages (ZIP files) to the Knowledge Center, and the Assistant can use what's in them to answer questions.

Open an asset in a side panel, a centered window, or full screen, from the Knowledge Center or from a source the Assistant cites.

Scroll through a PDF continuously or one page at a time, zoom in, rotate pages, and fit the document to your screen.

See how an asset is used in assignments: total assignments, completions, average days to complete, and activity over time.

Get a readable title when you upload a file. A file named 01-employee-handbook-2026.docx becomes Employee Handbook 2026, and the original file name stays the same for downloads.

Assign several assets at once to many people, each asset with its own due date and warning period.

Change your password from the User menu in a few steps, such as after you get a temporary one.

Add packs of expert-written commands to an Assistant, each grouped around a type of work. Each command relates to a common task, such as /quiz to test what you know or /roleplay to practice a conversation.

Rehearse a conversation before it happens, such as a sales call or a job interview. Type /roleplay in the Assistant and provide a topic. Joy plays the role of the other person, with coaching that helps you truly understand the content and a debrief at the end.

Explore a topic step by step with the Assistant's /learn command. Joy sets out a short plan, then asks you one question at a time, with hints when you get stuck.

Test what you know on any topic by typing /quiz in the Assistant. Answer each question in your own words and get multiple-choice options if you miss. Your score comes at the end.

Work through a realistic situation, such as responding to a safety incident at work. Use /scenario in the Assistant, decide what to do at each step, and see how it plays out, with a debrief at the end.

Commit key terms, figures, and steps to memory using /memorize in the Assistant. Joy asks about each one in different ways and keeps bringing back the ones you miss.

Talk to your SmarterU LMS in plain language with a native connector. Ask about enrollments, completions, and learner activity and get grounded answers. It's read-only and permission-aware, and it works alongside the LMS.

Ask a question in your own words and get an answer from content in the Knowledge Center, and from the web when it helps. Every answer shows its sources so you can check where it came from.

See helpful tips while the Assistant works on your answer, such as what you can ask or which commands to try. Admins can add their own tips for each Assistant or turn tips off.

Create specialized Assistants for different teams and topics, like an HR Assistant for policy questions or an Onboarding Coach for new hires. Give each one its own name, title, picture, and instructions, then assign it to the people who need it.

Continue any chat where you left off. Every chat is saved automatically and named after your first message. You can rename, favorite, archive, or delete chats to keep your history tidy.

Ask questions in the language you're most comfortable with and get answers in that same language, even when your content is written in English. You can also ask the Assistant to translate existing content into another language.

Copy the Assistant's response and paste it cleanly into an email or document. Links that only work inside Joy are removed automatically.

Save the requests you make most often as commands that you and your team can pick from a list, instead of typing them out each time. For example, create a Summarize Meeting command, then use it to turn meeting notes into a short summary.

Create downloadable Word, PowerPoint, Excel, and PDF documents by telling the Assistant what you need. For example, ask for a PowerPoint deck that introduces a new policy, or a PDF checklist for onboarding a new hire.

Describe the image you want and the Assistant creates it, from simple illustrations to photos and diagrams with readable text. Ask for changes until it looks right.

Get answers in the layout that fits best, such as tables, charts, timelines, flowcharts, mind maps, or forms. To get a specific format, just name it in your question.

Get charts, key numbers, and tables side by side. For example, ask for a dashboard of a sales spreadsheet in your Knowledge Center, then keep chatting to adjust what it shows.

Store all your knowledge assets (files and FlexDocs) in one hub, organized into folders and shown as cards. Search finds content by meaning as well as keywords, and the Assistant answers from what's stored here.

Organize assets into folders nested up to 10 levels deep, shown as a folder tree and as cards. Create, rename, and move folders by dragging, and get around with the tree or breadcrumbs.

Upload PDF, DOCX, PPT, PPTX, XLSX, CSV, TXT, PNG, JPEG, MP3, MP4, and WEBM files one at a time or in bulk. Preview, download, or assign these files as tasks, manage them from an admin panel (status, description, API ID), and ask the Assistant about them. You can also upload SCORM course packages for the Assistant to use.

Create customizable, collaborative documents made of pages with text, images, links, embedded media, and tables, for policy manuals, standard operating procedures (SOPs), and internal guides. View them full screen, assign them as tasks, and use them as sources for the Assistant.

Write in a block-based editor with a slash menu for inserting headings, lists, tables, columns, accordions, images, video and design embeds (YouTube, Vimeo, Figma), LaTeX equations, Excalidraw whiteboards, and voice dictation. Built-in AI writes content from a prompt and refines highlighted text (improve, summarize, expand, fix grammar), and you accept or reject each change.

Organize a FlexDoc into pages, like chapters, listed in a tree menu and nested up to 6 levels deep. Add, rename, reorder by dragging, nest, or delete pages.

Assign any Knowledge Center asset (such as a FlexDoc, PDF, or video) to the people who need it. Each assignment becomes a task on the recipient's Tasks page, with a subject and optional message.

Track tasks on a Kanban board across five stages (Not Started, In Progress, Warning, Overdue, and Completed), with My Tasks, Assigned by Me, and All Tasks views. A warning period you set flags tasks before their due date, and admins see every task in the organization.

Manage every user from one place: add, view, edit, search, and inactivate users, and manage detailed profiles (contact info, coordinators, time zone, preferred language, API ID). Your account always keeps at least one Admin, and inactive users can't sign in.

Give each person one of two roles across the workspace: Admin (full administrative access) or User (a streamlined day-to-day experience).

Ask for a chart, such as a bar or pie chart, or let the Assistant choose one when it's the clearest way to show the answer.

See key numbers as easy-to-read cards. For example, ask for a summary of a report and get its main figures, such as total sales or a completion rate, each in its own card.

Get flowcharts, Gantt charts, mind maps, and other diagrams in your answers so you can see how a process works or how the pieces fit together.

Get long answers broken into tables, tabs, and sections instead of one big block of text.

Get answers you can interact with, like flashcards to study from or side-by-side comparisons you can click through.

Generate content from a prompt (Write article, Create outline, Write blog post) and refine highlighted text (Improve writing, Make formal/casual, Summarize, Expand, Fix grammar, Explain concept) right in the editor. Accept or reject each change.

Embed YouTube, Vimeo, and Twitch videos, tweets, and Figma designs directly in a FlexDoc, alongside images with alt text and captions.

Insert LaTeX equations and Excalidraw whiteboard diagrams as blocks in a FlexDoc.

Dictate content into a FlexDoc using built-in speech-to-text.